local-codebase-indexer 0.3.0__tar.gz → 0.3.1__tar.gz

{local_codebase_indexer-0.3.0/local_codebase_indexer.egg-info → local_codebase_indexer-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: local-codebase-indexer
-Version: 0.3.0
+Version: 0.3.1
 Summary: Local codebase indexer and context provider for AI coding assistants: MCP server and CLI with SQL data-access and C# call relations. No cloud, no server.
 Author: sfy257000
 Project-URL: Homepage, https://github.com/sfy257000/local-codebase-indexer

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1}/TODO.md

@@ -4,6 +4,7 @@ Priorities come from the benchmark (`benchmarks/run_benchmark.py`, baseline in `
 
 ## Next
 
+0. **Publish to the MCP registry** (not done yet). PyPI 0.3.0 is out and carries the `mcp-name` marker; `server.json` is ready. Run `mcp-publisher login github` then `mcp-publisher publish` from the repo folder, then verify with `curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=local-codebase-indexer"`. Repeat after each release (bump both versions in `server.json`).
 1. **Check a real embedding model on your own machine** (this environment cannot reach Hugging Face, so the ONNX path is only tested with a tiny generated model). Export a model such as `all-MiniLM-L6-v2` (mean pooling) or `bge-small-en-v1.5` (`INDEXER_ONNX_POOLING=cls`, `INDEXER_ONNX_QUERY_PREFIX="Represent this sentence for searching relevant passages: "`), set `INDEXER_ONNX_MODEL`, and run `python benchmarks/run_benchmark.py --compare benchmarks/baseline.json`.
    Evidence: `synonym` Recall@5 is only 0.30 (hashing embedder plus the dictionary, which cannot cover free paraphrase). Whether a real model fixes this is not measured.
 2. **Resolve `FROM a JOIN b ON ..., c`** (a comma list after a JOIN loses `c`), non-sink SQL proc-name literals (`Run("usp_X")`), and EF query tracing (only the table mapping is recorded now).

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1}/local_codebase_indexer/__init__.py

@@ -1,3 +1,3 @@
 """Universal Local Codebase Indexer & Context Provider (see index.md)."""
 
-__version__ = "0.3.0"
+__version__ = "0.3.1"

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1}/local_codebase_indexer/cli.py

@@ -58,8 +58,25 @@ def build_parser() -> argparse.ArgumentParser:
     return p
 
 
+def _fix_stdio(serving: bool) -> None:
+    """MCP speaks UTF-8 JSON; the Windows locale codec (cp950, cp1252) would garble Chinese queries. On a console,
+    keep its encoding but never crash on a character it cannot show."""
+    for name in ("stdin", "stdout", "stderr"):
+        stream = getattr(sys, name, None)
+        if stream is None or not hasattr(stream, "reconfigure"):
+            continue
+        try:
+            if serving:
+                stream.reconfigure(encoding="utf-8", errors="replace")
+            elif name != "stdin":
+                stream.reconfigure(errors="replace")
+        except (OSError, ValueError):
+            pass
+
+
 def main(argv: list[str] | None = None) -> int:
     args = build_parser().parse_args(argv)
+    _fix_stdio(serving=args.cmd == "serve")
     root = os.path.abspath(args.root)
 
     if args.cmd == "serve":

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1}/local_codebase_indexer/core.py

@@ -61,7 +61,7 @@ def git_info(root: str) -> dict | None:
     """HEAD commit, branch and number of uncommitted paths; None outside a git work tree."""
     def run(*args: str) -> str | None:
         try:
-            r = subprocess.run(["git", "-C", root, *args], capture_output=True, text=True, timeout=15)
+            r = subprocess.run(["git", "-C", root, *args], capture_output=True, text=True, encoding="utf-8", errors="replace", timeout=15)
         except (OSError, subprocess.SubprocessError):
             return None
         return r.stdout if r.returncode == 0 else None

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1/local_codebase_indexer.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: local-codebase-indexer
-Version: 0.3.0
+Version: 0.3.1
 Summary: Local codebase indexer and context provider for AI coding assistants: MCP server and CLI with SQL data-access and C# call relations. No cloud, no server.
 Author: sfy257000
 Project-URL: Homepage, https://github.com/sfy257000/local-codebase-indexer

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1}/server.json

@@ -7,12 +7,12 @@
     "url": "https://github.com/sfy257000/local-codebase-indexer",
     "source": "github"
   },
-  "version": "0.3.0",
+  "version": "0.3.1",
   "packages": [
     {
       "registryType": "pypi",
       "identifier": "local-codebase-indexer",
-      "version": "0.3.0",
+      "version": "0.3.1",
       "runtimeHint": "uvx",
       "transport": {
         "type": "stdio"

{local_codebase_indexer-0.3.0 → local_codebase_indexer-0.3.1}/tests/test_indexer.py

@@ -330,3 +330,30 @@ def test_benchmark_corpus_is_valid_and_floor_holds(tmp_path):
     cats = json.loads(out.read_text(encoding="utf-8"))["suites"]["synthetic"]["categories"]
     assert cats["exact_identifier"]["recall5"] == 1.0
     assert cats["chinese"]["recall5"] == 1.0
+
+
+def test_git_output_is_decoded_as_utf8_not_the_locale(tmp_path, monkeypatch):
+    """On Windows the locale codec (cp950) cannot decode git's UTF-8 output and the reader thread crashed."""
+    import subprocess
+
+    import local_codebase_indexer.core as core
+    seen = {}
+    real = subprocess.run
+
+    def spy(*a, **kw):
+        seen.update(kw)
+        return real(*a, **kw)
+
+    monkeypatch.setattr(subprocess, "run", spy)
+    core.git_info(str(tmp_path))
+    assert seen.get("encoding") == "utf-8" and seen.get("errors") == "replace"
+
+
+def test_mcp_serve_reads_utf8_even_when_locale_is_cp950(project):
+    q = json.dumps({"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {
+        "name": "codebase_semantic_search", "arguments": {"query": "批號 LotNo", "limit": 2}}}, ensure_ascii=False)
+    env = dict(os.environ, PYTHONIOENCODING="cp950")
+    r = subprocess.run([sys.executable, "-m", "local_codebase_indexer", "--root", str(project), "serve"],
+                       input=(q + "\n").encode("utf-8"), capture_output=True, env=env, cwd=ROOT, timeout=60)
+    out = json.loads(r.stdout.decode("utf-8"))
+    assert "result" in out and "error" not in out, r.stderr.decode("utf-8", "replace")